Machine Learning Foundations: A Case Study Approach

This Specialization from leading researchers at the University of Washington introduces you to the exciting, high-demand field of Machine Learning. Through a series of practical case studies, you will gain applied experience in major areas of Machine Learning including Prediction, Classification, Clustering, and Information Retrieval. You will learn to analyze large and complex datasets, create systems that adapt and improve over time, and build intelligent applications that can make predictions from data.

Created by: Carlos Guestrin

icon
Quality Score

Content Quality
/
Video Quality
/
Qualified Instructor
/
Course Pace
/
Course Depth & Coverage
/

Overall Score : 96 / 100

icon
Course Description

Do you have data and wonder what it can tell you? Do you need a deeper understanding of the core ways in which machine learning can improve your business? Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems?In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images. Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains.This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications.Learning Outcomes: By the end of this course, you will be able to:-Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering.-Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning.-Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task.-Utilize a dataset to fit a model to analyze new data.-Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python.

icon
Instructor Details

Carlos Guestrin

Carlos Guestrin is the Amazon Professor of Machine Learning at the Computer Science & Engineering Department of the University of Washington. He is also a co-founder and CEO of Dato, Inc., focusing on making it easy to build intelligent applications that use large-scale machine learning at their core. His previous positions include the Finmeccanica Associate Professor at Carnegie Mellon University and senior researcher at the Intel Research Lab in Berkeley. Carlos is a recipient of a National Science Foundation CAREER Award, an Alfred P. Sloan Fellowship, and the Stanford Centennial Teaching Assistant Award. Carlos was also named one of the 2008 `Brilliant 10' by Popular Science Magazine, received the IJCAI Computers and Thought Award from the top AI conference, and the Presidential Early Career Award for Scientists and Engineers (PECASE) from President Obama.

icon
Reviews

4.8

981 total reviews

5 star 4 star 3 star 2 star 1 star
% Complete
% Complete
% Complete
% Complete
% Complete

By Ravi P on 8-Sep-18

The materials used in this course are extremely outdated. In order to access the data to do the projects you have to use SFrame, which is only supported up to Python 3.4.x. Python is currently on v 3.7.0. The data should be provided as .txt or .csv to be more universal. The instructors claim that you don't have to use a specific library to do this course, but you have to have at least SFrame in order to access the data! Further I am sure SFrame and Graphlab are good tools, but the course should be taught with open source tools so that the students can continue to use those tools after the course is over. I wanted to like this course. I did enjoy the professor's teaching styles, but the fact that I would have to download a new outdated python environment, and non universally accepted tools, to even access the data is a major deal breaker!

By Oscar A R on 24-Oct-18

I spend two days trying to get the graphlap lib working on two OS, and could not. I had to spend couple of hours setting up the aws services to be able to work with the samples.Phd's I dont think they make good teachers....Thanks.

By Ibrahim M A on 29-Apr-17

My only happiest moment in this whole course is writing this review, I couldn't wait to finish it in order to give it the 1 star rating it deserved. What I've seen from this course so far is abandonment , that's right this course is abandon ware, no questions get answered on the forums (asked a question a month ago and still didn't get an answer) and the links are outdated (links to further documentation don't work). I wouldn't recommend this course to anyone wanting to learn Machine learning since the instructors use proprietary libraries that need a license to use outside this course thus application wise what you learn her isn't transferable only the conceptual content;however, even in that there isn't much content for, since everything is an introduction here so nothing is quite useful . If your on a tight budget and your taking this specialization you could skip this course. Actually you could even skip this specialization since they canceled the capstone project so investing any money and time here is a waste. I can only recommend this specialization/course IF the instructors add a project at the end , be more involved on the forums , update non functional links ,and finally USE NON PROPRIETARY libraries hence they will need to take feedback from the students and redo most components of this specialization.

By Gianmaria M on 22-Jan-19

Very relevant material clearly explained by the professors, who are very knowledgeable and engageing. However the installation and usage of the GraphLab module is cumbersome and plagued with bugs. This could still work if there was enough support however I did not find any helpfrom the mentors/tutors who simply did not answer my questions in the Forum thus making my experience even more frustrating. Pity, I certainly hope Coursera can fix it as the class is quite good

By sreeraj c on 21-Jan-18

Such a bad presentation with no help to people with graphiclab tool setup.

By Sourav S on 27-Jun-18

Too dependent on Sframes and graphlab which does not work most of the times. I had to spend an entire day just figuring out versions of python to make this work.

By Jatin K P on 28-Mar-18

To follow along the course you need to install Graphlab library, which is the biggest challenge. Also, the support you get from the creators are not good enough.I regret to waste my time on this course.

By Ernie M on 25-Sep-17

I enrolled in this specialization to learn machine learning using GraphLab Create. Half way into the specialization the creators sold Turi, GrapLab's parent company, making it non available to the general public (not even by paying) and then all the knowledge devalued. I wish I had known this and I would have enrolled on a different specialization. The creators still give you the possibility of using numpy, scikit learn and pandas but I had already done a lot with GraphLab create. The time I invested on my nights after work became a waste. I was trying to convince the company I worked for to buy licenses for GraphLab create. Coursera should not allow folks to create courses that promote a private license course because it would make people waste their time and money if they decide to privatize the software. Don't take this course, and if you take it then only use GraphLab create when the authors give you no other option. Teaching style: Carlos was good, Emily is not very clear and loses focus of the topics and often rambles. She seems very knowledgeable but she lacks clarity of exposition when compared to Carlos or Andrew Ng.

By Andrew W on 4-Nov-17

Requires software called Graphlab Create that would not install on my machine. Unable to complete any of the course material due to this.

By Rahul D on 23-Dec-17

Course uses proprietary packages. Better learning from "The Analytics Edge" conducted by MIT at Edx.org

By Elvin V on 26-Oct-17

The worse course I have ever taken on Coursera. Forcing you to use their own library which is also not open source and free is ridiculous! You will never use graphlab in the future and there are better alternatives available! Totally useless experience. And most of the time vide lectures are just some mumbo jumbo, like showing diapers or napkins for 2 minutes! I have successfully wasted a lot of time on this course.

By Walther A G L M on 2-Jul-18

relying on proprietary library and unreliable notebook made this experience painful